© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1829
    Prev
    Next
    INDEX
    Explanations

    Kobe, Knicks, Spurs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪ»èĭ¦
    -0.09
     dụng
    -0.09
    _charset
    -0.09
    kish
    -0.09
    atest
    -0.09
    itag
    -0.09
    ught
    -0.08
     Gors
    -0.08
    essim
    -0.08
    aged
    -0.08
    POSITIVE LOGITS
    ÙĬÙĪÙĨ
    0.09
    æŶåĢĻ
    0.09
    鼩
    0.08
    çĴĺ
    0.08
    ours
    0.08
    вол
    0.08
    ä¸įåıĺ
    0.08
    ä¸įä½ı
    0.07
     Lords
    0.07
    è¡®
    0.07
    Activations Density 0.001%

    No Known Activations